mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-24 01:29:57 +08:00
[FDConfig] disable chunked_mm_input in ernie5 (#5774)
* disable chunked_mm_input in ernie5 * update code * update code * update test case * update testcase * upate case
This commit is contained in:
@@ -32,6 +32,7 @@ from fastdeploy.cache_manager.multimodal_cache_manager import (
|
||||
EncoderCacheManager,
|
||||
ProcessorCacheManager,
|
||||
)
|
||||
from fastdeploy.config import ErnieArchitectures
|
||||
from fastdeploy.engine.request import (
|
||||
ImagePosition,
|
||||
Request,
|
||||
@@ -680,7 +681,7 @@ class ResourceManagerV1(ResourceManager):
|
||||
|
||||
request = self.waiting[0]
|
||||
if (
|
||||
self.config.model_config.disable_mm_prefill_batch()
|
||||
ErnieArchitectures.is_ernie5_arch(self.config.model_config.architectures)
|
||||
and self._is_mm_request(request)
|
||||
and self.exist_mm_prefill(scheduled_reqs)
|
||||
) or (paddle.is_compiled_with_xpu() and self.exist_prefill(scheduled_reqs)):
|
||||
|
||||
Reference in New Issue
Block a user